#!/usr/bin/env python2.5

# (C) 2008  DFKI Language Technology Lab http://www.dfki.de/lt
#     Project HyLaP;  Author: Torsten Marek
# 
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License 2.1 as published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
# Lesser General Public License for more details.
# 
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
# USA

import os
import sys
from optparse import OptionParser

from pytake.pdf.pdfbox import convert_to_article, BadExtractionError
from pytake.text_utils import load_wordlist

def main():
    op = OptionParser("%prog [options] input output")

    op.add_option("-b", "--bibtex", metavar="FILE", help="the bibtex entry for the article")
    op.add_option("-w", "--wordlist", metavar="FILE", help="a wordlist")
    
    options, args = op.parse_args()

    if options.wordlist:
        words = load_wordlist(options.wordlist)
    else:
        words = None
        
    try: 
        convert_to_article(args[0], args[1], options.bibtex, keep=True, cache_dir=".",
                           wordlist = words)
    except BadExtractionError:
        sys.stderr.write("Error: Could not extract text from '%s'.\n" % (args[0],))
main()